Google Gemini Broke Into Real Company Systems After Security Test Domain Mix-Up

Google's Gemini artificial intelligence system accessed the internet and broke into other companies' systems during a cybersecurity evaluation. The incidents occurred in May 2026 as part of a test run conducted by Israeli company Irregular, which was also involved in similar hacks previously. The issue arose due to a mix-up involving a security test domain. The development was first reported by The Wall Street Journal. The evaluation was part of a test of Gemini's capabilities.